# Detecting Machine-Generated Texts: Not Just "AI vs Humans" and Explainability is Complicated

arXiv: https://arxiv.org/abs/2406.18259 · HTML: https://mlsanity.com/paper/2406.18259/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 42 references that are in the map.
- First posted on arXiv 26 Jun 2024.

## Builds on (most cited first, 19 of 19)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [ELI5: Long Form Question Answering](https://mlsanity.com/paper/1907.09190/) (2019)
- [Release Strategies and the Social Impacts of Language Models](https://mlsanity.com/paper/1908.09203/) (2019)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2401.12070/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [MGTBench: Benchmarking Machine-Generated Text Detection](https://mlsanity.com/paper/2303.14822/) (2023)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [A Survey on Detection of LLMs-Generated Content](https://mlsanity.com/paper/2310.15654/) (2023)
- [SeqXGPT: Sentence-Level AI-Generated Text Detection](https://mlsanity.com/paper/2310.08903/) (2023)
- [LLMDet: A Third Party Large Language Models Generated Text Detection Tool](https://mlsanity.com/paper/2305.15004/) (2023)
- [ConDA: Contrastive Domain Adaptation for AI-generated Text Detection](https://mlsanity.com/paper/2309.03992/) (2023)
- [From Text to Source: Results in Detecting Large Language Model-Generated Content](https://mlsanity.com/paper/2309.13322/) (2023)
- [Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy](https://mlsanity.com/paper/2402.16041/) (2024)
- [Classification of Human- and AI-Generated Texts: Investigating Features for ChatGPT](https://mlsanity.com/paper/2308.05341/) (2023)

## Built on by (most cited first, 15 of 15)

- [The Impact of Large Language Models in Academia: from Writing to Speaking](https://mlsanity.com/paper/2409.13686/) (2024)
- [Survey on AI-Generated Media Detection: From Non-MLLM to MLLM](https://mlsanity.com/paper/2502.05240/) (2025)
- [Assessing the Human Likeness of AI-Generated Counterspeech](https://mlsanity.com/paper/2410.11007/) (2024)
- [Every Step Counts: Decoding Trajectories as Authorship Fingerprints of dLLMs](https://mlsanity.com/paper/2510.05148/) (2025)
- [On the Detectability of LLM-Generated Text: What Exactly Is LLM-Generated Text?](https://mlsanity.com/paper/2510.20810/) (2025)
- [EMMM, Explain Me My Model! Explainable Machine Generated Text Detection in Dialogues](https://mlsanity.com/paper/2508.18715/) (2025)
- [Why AI-Generated Text Detection Fails: Evidence from Explainable AI Beyond Benchmark Accuracy](https://mlsanity.com/paper/2603.23146/) (2026)
- [ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability](https://mlsanity.com/paper/2502.11336/) (2025)
- ["I know myself better, but not really greatly": How Well Can LLMs Detect and Explain LLM-Generated Texts?](https://mlsanity.com/paper/2502.12743/) (2025)
- [Who Wrote This? Identifying Machine vs Human-Generated Text in Hausa](https://mlsanity.com/paper/2503.13101/) (2025)
- [Stylometry Analysis of Human and Machine Text for Academic Integrity](https://mlsanity.com/paper/2601.01225/) (2026)
- [READER: Reasoning-Enhanced AI-Generated Text Detection](https://mlsanity.com/paper/2605.25281/) (2026)
- [Show, Don't TELL: Explainable AI-Generated Text Detection](https://mlsanity.com/paper/2605.27921/) (2026)
- [A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models](https://mlsanity.com/paper/2606.04177/) (2026)
- [Using LLMs to Detect LLM-Generated Texts: A Cross-Generation Analysis](https://mlsanity.com/paper/2609.34691/) (2026)

## Abstract (arXiv)

As LLMs rapidly advance, increasing concerns arise regarding risks about actual authorship of texts we see online and in real world. The task of distinguishing LLM-authored texts is complicated by the nuanced and overlapping behaviors of both machines and humans. In this paper, we challenge the current practice of considering LLM-generated text detection a binary classification task of differentiating human from AI. Instead, we introduce a novel ternary text classification scheme, adding an "undecided" category for texts that could be attributed to either source, and we show that this new category is crucial to understand how to make the detection result more explainable to lay users. This research shifts the paradigm from merely classifying to explaining machine-generated texts, emphasizing need for detectors to provide clear and understandable explanations to users. Our study involves creating four new datasets comprised of texts from various LLMs and human authors. Based on new datasets, we performed binary classification tests to ascertain the most effective SOTA detection methods and identified SOTA LLMs capable of producing harder-to-detect texts. We constructed a new dataset of texts generated by two top-performing LLMs and human authors, and asked three human annotators to produce ternary labels with explanation notes. This dataset was used to investigate how three top-performing SOTA detectors behave in new ternary classification context. Our results highlight why "undecided" category is much needed from the viewpoint of explainability. Additionally, we conducted an analysis of explainability of the three best-performing detectors and the explanation notes of the human annotators, revealing insights about the complexity of explainable detection of machine-generated texts. Finally, we propose guidelines for developing future detection systems with improved explanatory power.